CVE-2025-48944 vLLM Tool Schema allows DoS via Malformed pattern and type Fields

What is CVE-2025-48944?

CVE-2025-48944 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 30 May 2025. Any signed-in user can exploit it over the network, with no action from the victim.

Official description

vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference worker with a single request. The worker will remain down until it is restarted. Version 0.9.0 fixes the issue.

Weakness: CWE-20

Which versions are affected by CVE-2025-48944?

3 open source packages ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2025-48944?

Upgrade vllm to 0.9.0 or later.

Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.

Is CVE-2025-48944 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-48944 exists.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-vrq3-r879-7m65, PYSEC-2026-2023.